facebookresearch/maskrcnn-benchmark
Inference time increases linearly with batch size
オープン
#294 opened on 2018/12/20
help wanted
Repository metrics
- Stars
- (9,161 個のスター)
- PR merge metrics
- (30d に merged PR はありません)
説明
❓ Questions and Help
I tested the batch inference,this is result batch size time 1 0.22 2 0.42 4 0.84 6 1.2 8 crash OOM Why big batchsize doesn't save time?